Pith. sign in

REVIEW 1 cited by

Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.15995 v1 pith:RRGYSEOL submitted 2024-12-20 cs.CL cs.AIcs.SDeess.AS

classification cs.CLcs.AIcs.SDeess.AS
keywords modelingspeechconversationaldataapproachdata-centricenhancingmultimodal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for effective interaction. Our work introduces a data-centric customization approach for efficiently enhancing multimodal understanding in conversational speech modeling. Central to our contributions is a novel multi-task learning paradigm that involves designing auxiliary tasks to utilize a small amount of speech data. Our approach achieves state-of-the-art performance on the Spoken-SQuAD benchmark, using only 10% of the training data with open-weight models, establishing a robust and efficient framework for audio-centric conversational modeling. We also introduce ASK-QA, the first dataset for multi-turn spoken dialogue with ambiguous user requests and dynamic evaluation inputs. Code and data forthcoming.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs

    cs.CL 2025-05 conditional novelty 5.0 of 10

    SpokenNativQA is a human-recorded Arabic and English spoken question-answering benchmark built from MultiNativQA text pairs, with ASR and LLM baselines.

Pith tools